[PATCH v4 0/4] open/accept directly into io_uring fixed file table

From: Pavel Begunkov
Date: Wed Aug 25 2021 - 07:26:33 EST


Add an optional feature to open/accept directly into io_uring's fixed
file table bypassing the normal file table. Same behaviour if as the
snippet below, but in one operation:

sqe = io_uring_[open|accept]_prep();
io_uring_submit(sqe);
// ... once we get a CQE back
io_uring_register_files_update(uring_idx, (fd = cqe->res));
close((fd = cqe->res));

The idea is old, and was brough up and implemented a year ago by
Josh Triplett, though haven't sought the light.

The behaviour is controlled by setting sqe->file_index, where 0 implies
the old behaviour using normal file tables. If non-zero value is
specified, then it will behave as described and place the file into a
fixed file slot sqe->file_index - 1. A file table should be already
created, the slot should be valid and empty, otherwise the operation
will fail.

note: IOSQE_FIXED_FILE can't be used as a mode switch, because accept
takes a file, and it already uses the flag with a different meaning.

v2, since RFC:
- added attribution
- updated descriptions
- rebased

v3:
- EBADF if slot is already used (Josh Triplett)
- alias index with splice_fd_in (Josh Triplett)
- fix a bound check bug

v4:
- separate u32 fields to internally store indexes (Jens, Josh)

Pavel Begunkov (4):
net: add accept helper not installing fd
io_uring: openat directly into fixed fd table
io_uring: hand code io_accept() fd installing
io_uring: accept directly into fixed file table

fs/io_uring.c | 115 +++++++++++++++++++++++++++++-----
include/linux/socket.h | 3 +
include/uapi/linux/io_uring.h | 5 +-
net/socket.c | 71 +++++++++++----------
4 files changed, 143 insertions(+), 51 deletions(-)

--
2.32.0